Abstract

A novel algorithm to detect an optimal set of semantic lines is proposed in this work. We develop two networks: selection network (S-Net) and harmonization network (H-Net). First, S-Net computes the probabilities and offsets of line candidates. Second, we filter out irrelevant lines through a selection-and-removal process. Third, we construct a complete graph, whose edge weights are computed by H-Net. Finally, we determine a maximal weight clique representing an optimal set of semantic lines. Moreover, to assess the overall harmony of detected lines, we propose a novel metric, called HIoU. Experimental results demonstrate that the proposed algorithm can detect harmonious semantic lines effectively and efficiently.

Overview

Demo video

Publication

Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong, and Chang-Su Kim, "Harmonious Semantic Line Detection via Maximal Weight Clique Selection," accepted to Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[paper] [supp] [code]